VisGuardian: A Lightweight Group-based Privacy Control Technique For Front Camera Data From AR Glasses in Home Environments

2026-01-27

AI Summary

This work addresses the challenge of fine-grained privacy control for context-sensitive visual data captured by AR glasses in domestic settings, where existing permission mechanisms fall short—particularly when handling numerous sensitive objects and non-consenting individuals. The authors propose a lightweight, group-based visual permission control framework that automatically clusters objects according to privacy sensitivity, semantic category, or spatial proximity. By integrating real-time YOLO-based detection with a predefined classification schema, the system enables efficient multi-object visibility management through a single user action, complemented by a low-overhead occlusion strategy to ensure minimal latency and power consumption. Experimental results demonstrate a mAP50 of 0.6704, a processing latency of only 14.0 ms, and a marginal 1.7% increase in hourly power usage. A user study (N=24) further confirms significant improvements over slider-based and per-object baseline approaches in terms of speed, efficiency, and usability.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Privacy
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Responsible Web: Consent frameworks and practices on the web

Abstract

Always-on sensing of AI applications on AR glasses makes traditional permission techniques ill-suited for context-dependent visual data, especially within home environments. The home presents a highly challenging privacy context due to the high density of sensitive objects, and the frequent presence of non-consenting family members, and the intimate nature of daily routines, making it a critical focus area for scalable privacy control mechanisms. Existing fine-grained controls, while offering nuanced choices, are inefficient for managing multiple private objects. We propose VisGuardian, a fine-grained content-based visual permission technique for AR glasses. VisGuardian features a group-based control mechanism that enables users to efficiently manage permissions for multiple private objects. VisGuardian detects objects using YOLO and adopts a pre-classified schema to group them. By selecting a single object, users can efficiently obscure groups of related objects based on criteria including privacy sensitivity, object category, or spatial proximity. A technical evaluation shows VisGuardian achieves mAP50 of 0.6704 with only 14.0 ms latency and a 1.7% increase in battery consumption per hour. Furthermore, a user study (N=24) comparing VisGuardian to slider-based and object-based baselines found it to be significantly faster for setting permissions and was preferred by users for its efficiency, effectiveness, and ease of use.

Problem

• privacy control
• AR glasses
• home environment
• visual data
• always-on sensing

Innovation

• group-based privacy control
• AR glasses
• fine-grained visual permissions
• YOLO object detection
• home environment privacy